Weld signature monitoring method and apparatus

Abstract

A method monitors a weld signature of a welding apparatus by processing the signature through a neural network to recognize a pattern, and by classifying the weld signature in response to the pattern. The method determines if the weld signature is sufficiently different from training weld signatures stored in a database, and records the weld signature in the database when sufficiently different. The method tests a weld joint to determine values of different weld joint properties, and then correlates the signature with the weld data to validate the database. An apparatus monitors a weld signature during a welding process to predict welding joint quality, and includes a welding gun, a power supply, and a sensor for detecting welding voltage, current, and wire feed speed (WFS). A neural network receives the welding process values and classifies the signature into different weld classifications each corresponding to a predicted welding joint quality.

Description

technical field [0001] The present invention generally relates to a method and apparatus for monitoring weld signatures during a welding process by classifying them using a neural network model or a neural processor. Background technique [0002] Welding systems are widely used in various manufacturing processes to join or join different work surfaces. Arc welding systems, among other things, can be used to strongly fuse or merge separate work surfaces into one through the controlled application of intense heat and application of intermediate materials to form a composite weld joint. A strong metallurgical bond is formed when the intermediate material, which is rapidly melted by the high temperature electric arc present during the arc welding process, finally cools and solidifies. Ideally, the resulting welded joint has approximately the same overall strength and other material properties as the originally separated working surfaces. [0003] During arc welding, an arc can...

AI Technical Summary

Problems solved by technology

However, since the large number of different welding system and environmental operating variables are interrelated in complex ways to affect the quality of the welds obtained, monitoring the welding process in real time to accurately detect acceptable, "acceptable" or "good" welds can be critical. a challenging process

Algorithmically comparing different individual welding system variables to stored thresholds is also suboptimal due to the difficulty of accurately determining isolated or individual contributions or differential effects of specific variable values ​​on the overall quality of the resulting welded joint

Images